csbowei/ART
3122
1---2base_model: black-forest-labs/FLUX.1-Kontext-dev3base_model_relation: adapter4library_name: diffusers5license: cc-by-nc-sa-4.06tags:7- lora8- flux9- flux-kontext10- image-to-image11- makeup-transfer12- makeup-removal13- safetensors14---15 16<div align='center'>17<h1 align="center">[ECCV 2026] Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer</h1>18 Bo Wei<sup> 1*</sup> 19 <a href='https://scholar.google.com/citations?user=wLTXeNwAAAAJ&hl=en&oi=ao' target='_blank'>Xianhui Lin</a><sup> 2†</sup> 20 Yi Dong<sup> 2</sup> 21 Zhongzhong Li<sup> 2</sup> 22 Zonghui Li<sup> 2</sup> 23 <a href='https://scholar.google.com/citations?hl=en&user=BhmLztgAAAAJ' target='_blank'>Zirui Wang</a><sup> 2</sup> 24</div>25 26<div align='center'>27 <a href='https://scholar.google.com/citations?hl=en&user=12MzNVkAAAAJ' target='_blank'>Jiachen Yang</a><sup> 2</sup> 28 Xing Liu<sup> 2</sup> 29 Hong Gu<sup> 2</sup> 30 <a href='https://scholar.google.com/citations?hl=en&user=tmT_voUAAAAJ' target='_blank'>Xiaoming Li</a><sup> 3✉</sup> 31 <a href='https://scholar.google.com/citations?hl=en&user=rUOpCEYAAAAJ' target='_blank'>Wangmeng Zuo</a><sup> 1✉</sup>32</div>33 34<div align='center'>35 <sup>1 </sup>Harbin Institute of Technology 36 <sup>2 </sup>vivo BlueImage Lab 37 <sup>3 </sup>Nanjing University38</div>39 40<div align='center'>41 <small><sup>*</sup> Work done during an internship at vivo.</small> 42 <small><sup>†</sup> Project lead</small>43</div>44 45<div align="center">46 <p>47 <a href="https://arxiv.org/abs/2606.31089" target="_blank"><img src="https://img.shields.io/badge/arXiv-ART-red" alt="arXiv link"></a> 48 <a href="https://csbowei.github.io/ART/" target="_blank"><img src="https://img.shields.io/badge/Project-Homepage-green" alt="project homepage"></a> 49 <a href="https://github.com/csbowei/ART" target="_blank"><img src="https://img.shields.io/badge/GitHub-Code-blue?logo=github" alt="GitHub code"></a> 50 <a href="https://huggingface.co/spaces/csbowei/ART-Makeup-Transfer" target="_blank"><img src="https://img.shields.io/badge/🤗 Hugging Face-Space-orange" alt="HF Space"></a> 51 <a href="https://drive.google.com/drive/folders/1UfUUAk86fWWzYsZcGOzpTmAWa32IwK21?usp=drive_link" target="_blank"><img src="https://img.shields.io/badge/Dataset-MF2K-purple?logo=googledrive&logoColor=white" alt="MF2K Dataset"></a>52 </p>53</div>54 55This repository provides the model weights for **ART: Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer**.56 57ART is a makeup transfer framework that applies a reference cosmetic style to a source face while preserving identity, geometry, and fine-grained makeup details.58 59## Files60 61| File | Task |62| ----------------------------------- | --------------- |63| `art_transfer_lora_512.safetensors` | Makeup transfer |64| `art_transfer_lora_1024.safetensors` | Makeup transfer |65| `art_demakeup_lora_512.safetensors` | Makeup removal |66| `art_demakeup_lora_1024.safetensors` | Makeup removal |67 68Higher-resolution checkpoints are not planned for the current release.69 70## Usage71 72These LoRA adapters are for [`black-forest-labs/FLUX.1-Kontext-dev`](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev).73 74Refer to the project repository: https://github.com/csbowei/ART75 76Example:77 78```bash79# Makeup transfer: apply the reference's makeup onto the input face80python infer.py \81 --task mt \82 --input ./examples/source/src_001.jpg \83 --ref ./examples/ref/ref_001.jpg \84 --lora_path /path/to/art_transfer_lora_1024.safetensors \85 --resolution 102486```87 88```bash89# Makeup removal: strip cosmetics from the input face90python infer.py \91 --task demakeup \92 --input ./examples/ref/ref_002.jpg \93 --lora_path /path/to/art_demakeup_lora_1024.safetensors \94 --resolution 102495```96 97## Citation98 99```bibtex100@article{wei2026art,101 title={Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer},102 author={Wei, Bo and Lin, Xianhui and Dong, Yi and Li, Zhongzhong and Li, Zonghui and Wang, Zirui and Yang, Jiachen and Liu, Xing and Gu, Hong and Li, Xiaoming and Zuo, Wangmeng},103 journal={arXiv preprint arXiv:2606.31089},104 year={2026}105}106```